Papers by Xiaofang Zhao

6 papers
Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight (2020.acl-main)

Copied to clipboard

Challenge: Current state-of-the-art neural dialogue models learn from human conversations . however, due to the open-ended nature of human conversations, the quality of training data varies .
Approach: They propose a data manipulation framework to augment and highlight effective training samples . they also propose to increase its manipulation skills through gradient descent with validation samples a reshaping framework to proactively restructure the data distribution towards reliable samples is also proposed .
Outcome: The proposed framework improves the performance of open-domain neural dialogue models with respect to evaluation metrics and human judgments.
Group-wise Contrastive Learning for Neural Dialogue Generation (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to training dialogue models have low diversity in open-domain contexts . prior art suggests that naive MLE objective is not effective enough .
Approach: They propose to incorporate contrastive learning into dialogue generation by using a pretrained baseline model as a reference.
Outcome: The proposed framework is suited for training a wide range of dialogue generation models with favorable performance over baseline training approaches.
DIDS: Domain Impact-aware Data Sampling for Large Language Model Training (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact.
Approach: They propose to use a Fisher-Information Matrix-guided metric to measure domain impact to ensure intra-domain consistency and accuracy.
Outcome: The proposed model achieves 3.4% higher average performance while maintaining comparable training efficiency.
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for dialogue empathy focus on the emotion flow in one direction, from context to response.
Approach: They propose a dual-generative model to construct emotional consensus and use unpaired data to produce pseudo paired empathetic samples.
Outcome: The proposed model outperforms baseline models in producing coherent and empathetic responses.
Adaptive Parameterization for Neural Dialogue Generation (D19-1)

Copied to clipboard

Challenge: Existing models of open-domain dialogue generate responses based on sequence-to-sequence paradigms.
Approach: They propose an Adaptive Neural Dialogue generation model which manages various conversations with conversation-specific parameterization.
Outcome: The proposed model performs better on a large-scale conversational dataset.
Making RALM Robust to Irrelevant Contexts via Layer Knowledge Guided Attention (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) face factual hallucination and knowledge obsolescence when tackling knowledge-intensive tasks.
Approach: They propose a layer-knowledge guided attention method which harnesses the layer-wise knowledge of large language models to optimize per-layer attention on useful passages.
Outcome: The proposed method outperforms existing methods on RALM benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations